© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27931
    Prev
    Next
    INDEX
    Explanations

    references to recent events and deployments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    recently, currently, latest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.81
    出版年
    -0.77
     ujednoznacz
    -0.63
     חיצוניים
    -0.60
     habet
    -0.58
     subsequent
    -0.58
     sauvage
    -0.56
    明
    -0.56
     tiegħek
    -0.55
     ejus
    -0.54
    POSITIVE LOGITS
    íncia
    0.69
     оригіналу
    0.68
    RegistryLite
    0.66
     newOwner
    0.65
     onCancelled
    0.64
    ล่า
    0.63
     recientemente
    0.63
    recently
    0.63
    complexContent
    0.62
    ésultat
    0.61
    Activations Density 0.048%

    No Known Activations